
=== Start adding workers ===
=> Add worker SGDMWorker(index=0, momentum=0.9)
=> Add worker SGDMWorker(index=1, momentum=0.9)
=> Add worker SGDMWorker(index=2, momentum=0.9)
=> Add worker SGDMWorker(index=3, momentum=0.9)
=> Add worker SGDMWorker(index=4, momentum=0.9)
=> Add worker SGDMWorker(index=5, momentum=0.9)
=> Add worker SGDMWorker(index=6, momentum=0.9)
=> Add worker SGDMWorker(index=7, momentum=0.9)
=> Add worker SGDMWorker(index=8, momentum=0.9)
=> Add worker SGDMWorker(index=9, momentum=0.9)
=> Add worker ByzantineWorker(index=10)
=> Add worker ByzantineWorker(index=11)

=== Start adding graph ===
<codes.graph_utils.DumbbellVariant object at 0x7f1ba99939d0>

Train epoch 1
[E 1B0  |    384/60000 (  1%) ] Loss: 2.3109 top1=  9.6875

=== Peeking data label distribution E1B0 ===
Worker 0 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 1 has targets: tensor([2, 1, 4, 4, 0], device='cuda:0')
Worker 2 has targets: tensor([3, 1, 4, 1, 3], device='cuda:0')
Worker 3 has targets: tensor([2, 3, 0, 0, 1], device='cuda:0')
Worker 4 has targets: tensor([2, 1, 1, 4, 2], device='cuda:0')
Worker 5 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')
Worker 6 has targets: tensor([9, 9, 6, 7, 9], device='cuda:0')
Worker 7 has targets: tensor([7, 5, 7, 9, 5], device='cuda:0')
Worker 8 has targets: tensor([8, 9, 9, 5, 7], device='cuda:0')
Worker 9 has targets: tensor([8, 8, 7, 5, 9], device='cuda:0')
Worker 10 has targets: tensor([3, 0, 2, 2, 1], device='cuda:0')
Worker 11 has targets: tensor([6, 7, 6, 8, 6], device='cuda:0')


[E 1B10 |   4224/60000 (  7%) ] Loss: 1.0048 top1= 63.4375
[E 1B20 |   8064/60000 ( 13%) ] Loss: 0.2617 top1= 91.2500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6724 top1= 78.3654


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=9.4669 top1= 48.6178


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=7.3335 top1= 43.6298

Train epoch 2
[E 2B0  |    384/60000 (  1%) ] Loss: 0.3913 top1= 90.9375
[E 2B10 |   4224/60000 (  7%) ] Loss: 0.2609 top1= 91.8750
[E 2B20 |   8064/60000 ( 13%) ] Loss: 0.1588 top1= 94.0625

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.6570 top1= 84.7055


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8822 top1= 49.7997


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.8105 top1= 45.6030

Train epoch 3
[E 3B0  |    384/60000 (  1%) ] Loss: 0.1441 top1= 95.6250
[E 3B10 |   4224/60000 (  7%) ] Loss: 0.1283 top1= 95.6250
[E 3B20 |   8064/60000 ( 13%) ] Loss: 0.0797 top1= 97.8125

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.5283 top1= 86.2380


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.2396 top1= 49.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.7456 top1= 45.9936

Train epoch 4
[E 4B0  |    384/60000 (  1%) ] Loss: 0.0832 top1= 97.1875
[E 4B10 |   4224/60000 (  7%) ] Loss: 0.0689 top1= 96.5625
[E 4B20 |   8064/60000 ( 13%) ] Loss: 0.0558 top1= 98.7500

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.4498 top1= 87.4599


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=4.0780 top1= 50.2404


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.6457 top1= 46.0437

Train epoch 5
[E 5B0  |    384/60000 (  1%) ] Loss: 0.0541 top1= 98.1250
[E 5B10 |   4224/60000 (  7%) ] Loss: 0.0457 top1= 98.7500
[E 5B20 |   8064/60000 ( 13%) ] Loss: 0.0325 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3975 top1= 88.5817


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.8510 top1= 50.1603


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.5110 top1= 46.2440

Train epoch 6
[E 6B0  |    384/60000 (  1%) ] Loss: 0.0310 top1= 99.0625
[E 6B10 |   4224/60000 (  7%) ] Loss: 0.0435 top1= 99.0625
[E 6B20 |   8064/60000 ( 13%) ] Loss: 0.0218 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3627 top1= 88.8522


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.5523 top1= 50.4107


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.4129 top1= 46.7748

Train epoch 7
[E 7B0  |    384/60000 (  1%) ] Loss: 0.0155 top1=100.0000
[E 7B10 |   4224/60000 (  7%) ] Loss: 0.0247 top1= 99.3750
[E 7B20 |   8064/60000 ( 13%) ] Loss: 0.0196 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3560 top1= 88.3113


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=3.3411 top1= 50.4808


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.3182 top1= 47.7664

Train epoch 8
[E 8B0  |    384/60000 (  1%) ] Loss: 0.0184 top1=100.0000
[E 8B10 |   4224/60000 (  7%) ] Loss: 0.0197 top1= 99.6875
[E 8B20 |   8064/60000 ( 13%) ] Loss: 0.0151 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3450 top1= 88.6919


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.9943 top1= 51.9932


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=3.0835 top1= 49.2588

Train epoch 9
[E 9B0  |    384/60000 (  1%) ] Loss: 0.0140 top1=100.0000
[E 9B10 |   4224/60000 (  7%) ] Loss: 0.0243 top1= 99.6875
[E 9B20 |   8064/60000 ( 13%) ] Loss: 0.0177 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3331 top1= 89.3329


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.7311 top1= 54.0064


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.7564 top1= 51.3822

Train epoch 10
[E10B0  |    384/60000 (  1%) ] Loss: 0.0144 top1= 99.3750
[E10B10 |   4224/60000 (  7%) ] Loss: 0.0153 top1=100.0000
[E10B20 |   8064/60000 ( 13%) ] Loss: 0.0198 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3173 top1= 89.9639


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.6313 top1= 55.2284


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.4260 top1= 52.9748

Train epoch 11
[E11B0  |    384/60000 (  1%) ] Loss: 0.0152 top1= 99.6875
[E11B10 |   4224/60000 (  7%) ] Loss: 0.0180 top1= 99.6875
[E11B20 |   8064/60000 ( 13%) ] Loss: 0.0075 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3412 top1= 88.6218


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3450 top1= 57.1214


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.3072 top1= 54.9980

Train epoch 12
[E12B0  |    384/60000 (  1%) ] Loss: 0.0215 top1= 99.6875
[E12B10 |   4224/60000 (  7%) ] Loss: 0.0203 top1= 99.3750
[E12B20 |   8064/60000 ( 13%) ] Loss: 0.0410 top1= 98.1250

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3515 top1= 88.2011


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.3429 top1= 58.5837


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.1187 top1= 57.0813

Train epoch 13
[E13B0  |    384/60000 (  1%) ] Loss: 0.0239 top1= 99.0625
[E13B10 |   4224/60000 (  7%) ] Loss: 0.0175 top1= 99.3750
[E13B20 |   8064/60000 ( 13%) ] Loss: 0.0099 top1= 99.6875

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.3048 top1= 90.1943


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1639 top1= 59.6755


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=2.0922 top1= 55.7592

Train epoch 14
[E14B0  |    384/60000 (  1%) ] Loss: 0.0138 top1=100.0000
[E14B10 |   4224/60000 (  7%) ] Loss: 0.0186 top1= 99.3750
[E14B20 |   8064/60000 ( 13%) ] Loss: 0.0051 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2892 top1= 90.6951


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1701 top1= 59.8758


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.7342 top1= 60.4067

Train epoch 15
[E15B0  |    384/60000 (  1%) ] Loss: 0.0065 top1=100.0000
[E15B10 |   4224/60000 (  7%) ] Loss: 0.0077 top1=100.0000
[E15B20 |   8064/60000 ( 13%) ] Loss: 0.0085 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2819 top1= 91.3061


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=2.1696 top1= 60.3566


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.6049 top1= 62.7304

Train epoch 16
[E16B0  |    384/60000 (  1%) ] Loss: 0.0140 top1= 99.6875
[E16B10 |   4224/60000 (  7%) ] Loss: 0.0156 top1= 99.6875
[E16B20 |   8064/60000 ( 13%) ] Loss: 0.0043 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2785 top1= 91.3361


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.6705 top1= 65.6550


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3043 top1= 66.9271

Train epoch 17
[E17B0  |    384/60000 (  1%) ] Loss: 0.0049 top1=100.0000
[E17B10 |   4224/60000 (  7%) ] Loss: 0.0060 top1=100.0000
[E17B20 |   8064/60000 ( 13%) ] Loss: 0.0056 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2753 top1= 91.7067


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.5778 top1= 67.1474


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.3110 top1= 68.9904

Train epoch 18
[E18B0  |    384/60000 (  1%) ] Loss: 0.0045 top1=100.0000
[E18B10 |   4224/60000 (  7%) ] Loss: 0.0068 top1=100.0000
[E18B20 |   8064/60000 ( 13%) ] Loss: 0.0039 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2710 top1= 91.8069


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.2718 top1= 70.8634


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.2812 top1= 70.0821

Train epoch 19
[E19B0  |    384/60000 (  1%) ] Loss: 0.0056 top1=100.0000
[E19B10 |   4224/60000 (  7%) ] Loss: 0.0043 top1=100.0000
[E19B20 |   8064/60000 ( 13%) ] Loss: 0.0031 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2608 top1= 92.4079


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.1108 top1= 73.7280


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=1.1096 top1= 72.6663

Train epoch 20
[E20B0  |    384/60000 (  1%) ] Loss: 0.0037 top1=100.0000
[E20B10 |   4224/60000 (  7%) ] Loss: 0.0032 top1=100.0000
[E20B20 |   8064/60000 ( 13%) ] Loss: 0.0028 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2590 top1= 92.5381


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=1.0477 top1= 74.9900


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.9297 top1= 76.6326

Train epoch 21
[E21B0  |    384/60000 (  1%) ] Loss: 0.0034 top1=100.0000
[E21B10 |   4224/60000 (  7%) ] Loss: 0.0024 top1=100.0000
[E21B20 |   8064/60000 ( 13%) ] Loss: 0.0025 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2581 top1= 92.6583


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.9622 top1= 76.8730


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.8099 top1= 79.4872

Train epoch 22
[E22B0  |    384/60000 (  1%) ] Loss: 0.0031 top1=100.0000
[E22B10 |   4224/60000 (  7%) ] Loss: 0.0023 top1=100.0000
[E22B20 |   8064/60000 ( 13%) ] Loss: 0.0024 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2584 top1= 92.7384


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.8769 top1= 78.3454


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.7207 top1= 81.8109

Train epoch 23
[E23B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E23B10 |   4224/60000 (  7%) ] Loss: 0.0020 top1=100.0000
[E23B20 |   8064/60000 ( 13%) ] Loss: 0.0020 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2588 top1= 92.8085


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7806 top1= 80.3285


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.6341 top1= 83.8742

Train epoch 24
[E24B0  |    384/60000 (  1%) ] Loss: 0.0027 top1=100.0000
[E24B10 |   4224/60000 (  7%) ] Loss: 0.0019 top1=100.0000
[E24B20 |   8064/60000 ( 13%) ] Loss: 0.0018 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2596 top1= 92.9387


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.7023 top1= 82.2917


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5748 top1= 85.2063

Train epoch 25
[E25B0  |    384/60000 (  1%) ] Loss: 0.0026 top1=100.0000
[E25B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E25B20 |   8064/60000 ( 13%) ] Loss: 0.0016 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2604 top1= 93.0389


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.6406 top1= 83.9243


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5384 top1= 86.2680

Train epoch 26
[E26B0  |    384/60000 (  1%) ] Loss: 0.0024 top1=100.0000
[E26B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E26B20 |   8064/60000 ( 13%) ] Loss: 0.0015 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2613 top1= 93.1991


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5961 top1= 85.1562


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.5129 top1= 87.0493

Train epoch 27
[E27B0  |    384/60000 (  1%) ] Loss: 0.0022 top1=100.0000
[E27B10 |   4224/60000 (  7%) ] Loss: 0.0018 top1=100.0000
[E27B20 |   8064/60000 ( 13%) ] Loss: 0.0014 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2622 top1= 93.2792


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5599 top1= 86.0877


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4949 top1= 87.5200

Train epoch 28
[E28B0  |    384/60000 (  1%) ] Loss: 0.0020 top1=100.0000
[E28B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E28B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2630 top1= 93.3594


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5303 top1= 86.8790


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4813 top1= 87.9708

Train epoch 29
[E29B0  |    384/60000 (  1%) ] Loss: 0.0019 top1=100.0000
[E29B10 |   4224/60000 (  7%) ] Loss: 0.0017 top1=100.0000
[E29B20 |   8064/60000 ( 13%) ] Loss: 0.0013 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2637 top1= 93.3694


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.5126 top1= 87.5300


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4771 top1= 88.1210

Train epoch 30
[E30B0  |    384/60000 (  1%) ] Loss: 0.0017 top1=100.0000
[E30B10 |   4224/60000 (  7%) ] Loss: 0.0016 top1=100.0000
[E30B20 |   8064/60000 ( 13%) ] Loss: 0.0012 top1=100.0000

=> Averaged model (Global Average Validation Accuracy) | Eval Loss=0.2644 top1= 93.3894


=> Averaged model (Clique1 Average Validation Accuracy) | Eval Loss=0.4971 top1= 88.1410


=> Averaged model (Clique2 Average Validation Accuracy) | Eval Loss=0.4731 top1= 88.3514

